In this paper, we investigate the feasibility of applying few-shot learning algorithms to a speech task. We formulate a user-defined scenario of spoken term classification as a few-shot learning problem. In most few-shot learning studies, it is assumed that all the N classes are new in a N-way problem. We suggest that this assumption can be relaxed and define a N+M-way problem where N and M are the number of new classes and fixed classes respectively. We propose a modification to the Model-Agnostic Meta-Learning (MAML) algorithm to solve the problem. Experiments on the Google Speech Commands dataset show that our approach outperforms the conventional supervised learning approach and the original MAML.
@article{arxiv.1812.10233,
title = {An Investigation of Few-Shot Learning in Spoken Term Classification},
author = {Yangbin Chen and Tom Ko and Lifeng Shang and Xiao Chen and Xin Jiang and Qing Li},
journal= {arXiv preprint arXiv:1812.10233},
year = {2020}
}